Nicola Bordin

ContrasTED: contrastive domain embeddings for scalable remote homology classification

ContrasTED improves homology classification by using contrastive learning to assign domains to superfamilies with high accuracy, outperforming existing methods.

FrustrAI-Seq: Scaling Local Energetic Frustration to the Protein Sequence Space

A fine-tuned ProtT5 protein language model predicts per-residue energetic frustration from sequence (Pearson r 0.86 on unseen CATH topologies) and profiles the human proteome in ~17 minutes on one GPU.

On the state of protein function prediction: a report on the fourth CAFA challenge

This paper reports on the fourth CAFA challenge, showing improvements in Gene Ontology term prediction but highlighting challenges in new evaluation settings.

ProFam: Open-Source Protein Family Language Modelling for Fitness Prediction and Design

ProFam is an open-source protein family language model that improves fitness prediction and design by leveraging evolutionary context through homologous sequences.

Metagenomic-scale analysis of the predicted protein structure universe

The paper combines AlphaFold and ESMfold predictions to create a large structural dataset, identifies novel protein folds and domain combinations, and highlights the value of metagenomic data for structural diversity.

Exploring structural diversity across the protein universe with The Encyclopedia of Domains

The paper introduces TED, a resource that segments and classifies over 370 million domains from the AlphaFold Protein Structure Database, expanding known structural domains and uncovering new structural interactions.

Predicting human and viral protein variants affecting COVID-19 susceptibility and repurposing therapeutics

The paper predicts human and viral protein variants that enhance SARS-CoV-2 binding affinity and may increase COVID-19 susceptibility.

Chainsaw: protein domain segmentation with fullyconvolutional neural networks

Chainsaw uses a fully convolutional neural network to predict protein domain boundaries, achieving higher accuracy than existing methods in domain segmentation.

The Streptococcus pneumoniae transcriptome in patient cerebrospinal fluid identifies novel virulence factors required for meningitis

The paper uses RNA sequencing of cerebrospinal fluid from meningitis patients to identify S. pneumoniae virulence factors, finding two genes linked to increased mortality and reduced infection persistence.

Broad functional profiling of fission yeast proteins using phenomics and machine learning

The paper uses phenomics and machine learning to predict protein functions in fission yeast, identifying novel roles and validating predictions through experimental validation.

AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms

The paper uses AlphaFold2 to analyze protein structures from 21 organisms, identifying 26 novel superfamilies and expanding structural diversity insights.

CATHe: Detection of remote homologues for CATH superfamilies using embeddings from protein language models

The paper introduces CATHe, a method using protein language model embeddings to detect remote homologues for CATH superfamilies, achieving high accuracy and validating predictions with AlphaFold structures.

Characterizing and explaining impact of disease-associated mutations in proteins without known structures or structural homologues

The paper predicts structures of disease-associated proteins without known structures, identifies functional sites, and explains 80% of mutations based on their proximity to these sites or structural impact.

Contrastive learning on protein embeddings enlightens midnight zone

This paper introduces ProtTucker, a contrastive learning method using protein embeddings from pLMs to improve recognition of distant homologous relationships in the midnight zone of protein similarity.

Streamlined use of protein structures in variant analysis

The paper presents a streamlined system for integrating 3D protein structures into variant analysis, enabling easy variant specification and access to structural insights.

Clustering FunFams using sequence embeddings improves EC purity

The paper improves the purity of protein functional families by clustering them using sequence embeddings, doubling the number of pure clusters per family.

SARS-CoV-2 spike protein predicted to form complexes with host receptor protein orthologues from a broad range of mammals

The paper predicts SARS-CoV-2 spike protein interactions with ACE2 orthologues across 215 vertebrates, finds mutations in ACE2 are more detrimental, and shows human strains are present in animals.

SARS-CoV-2 structural coverage map reveals state changes that disrupt host immunity

The paper generates 872 structural models of SARS-CoV-2 proteins and creates a structural coverage map to help researchers understand viral mechanisms and immune disruption.